long_T5_sum_outcome

floflodebilbao/long_T5_sum_outcome

long_T5_sum_outcome is a machine learning model from floflodebilbao. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for transformers. The card lists the license as apache-2.0.

should probably proofread and complete it, then remove this comment. --

Downloads · 30 days

40% of all-time downloads

All-time downloads

Public

Parameters

297M

10.7 GB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors1.2 GB · 100%

At a glance

Library: transformers
License: apache-2.0
Model type: longt5
Access: Public
Created: Jul 8, 2025
Updated: Jul 30, 2025
SHA: e573340d

Base models

google/long-t5-tglobal-base

Model card

From the Hugging Face model README

long_T5_sum_outcome

This model is a fine-tuned version of google/long-t5-tglobal-base on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 16.6670
Rouge1: 0.179
Rouge2: 0.0376
Rougel: 0.1311
Rougelsum: 0.1303
Gen Len: 31.0
Bleu: 0.0183
Precisions: 0.0456
Brevity Penalty: 0.952
Length Ratio: 0.9531
Translation Length: 1117.0
Reference Length: 1172.0
Precision: 0.839
Recall: 0.8508
F1: 0.8447
Hashcode: roberta-large_L17_no-idf_version=0.3.12(hug_trans=4.53.1)

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 2e-05
train_batch_size: 1
eval_batch_size: 1
seed: 42
gradient_accumulation_steps: 16
total_train_batch_size: 16
optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len	Bleu	Precisions	Brevity Penalty	Length Ratio	Translation Length	Reference Length	Precision	Recall	F1	Hashcode
26.8047	1.0	7	28.1961	0.1991	0.0452	0.1451	0.1451	31.0	0.0226	0.0516	0.9697	0.9701	1137.0	1172.0	0.8417	0.854	0.8477	roberta-large_L17_no-idf_version=0.3.12(hug_trans=4.53.1)
24.4577	2.0	14	25.5517	0.1938	0.0452	0.1398	0.14	31.0	0.0225	0.0511	0.9617	0.9625	1128.0	1172.0	0.8404	0.8526	0.8464	roberta-large_L17_no-idf_version=0.3.12(hug_trans=4.53.1)
22.7574	3.0	21	23.4583	0.1872	0.0412	0.1373	0.1368	31.0	0.0218	0.0488	0.9582	0.959	1124.0	1172.0	0.8393	0.8517	0.8454	roberta-large_L17_no-idf_version=0.3.12(hug_trans=4.53.1)
21.0685	4.0	28	21.7844	0.1858	0.0425	0.1358	0.1353	31.0	0.0196	0.0485	0.9635	0.9642	1130.0	1172.0	0.8407	0.8525	0.8465	roberta-large_L17_no-idf_version=0.3.12(hug_trans=4.53.1)
20.037	5.0	35	20.3738	0.1858	0.0425	0.1358	0.1353	31.0	0.0196	0.0485	0.9635	0.9642	1130.0	1172.0	0.8407	0.8525	0.8465	roberta-large_L17_no-idf_version=0.3.12(hug_trans=4.53.1)
18.9602	6.0	42	19.1832	0.1862	0.0397	0.1322	0.1313	31.0	0.0194	0.0484	0.9546	0.9556	1120.0	1172.0	0.8396	0.8512	0.8453	roberta-large_L17_no-idf_version=0.3.12(hug_trans=4.53.1)
18.0035	7.0	49	18.1774	0.1853	0.0397	0.1321	0.1313	31.0	0.0194	0.0482	0.9555	0.9565	1121.0	1172.0	0.8394	0.8511	0.8451	roberta-large_L17_no-idf_version=0.3.12(hug_trans=4.53.1)
17.2636	8.0	56	17.4050	0.1862	0.0396	0.1328	0.132	31.0	0.0195	0.0478	0.9493	0.9505	1114.0	1172.0	0.8389	0.8507	0.8447	roberta-large_L17_no-idf_version=0.3.12(hug_trans=4.53.1)
16.5914	9.0	63	16.8775	0.179	0.0376	0.1302	0.1293	31.0	0.019	0.046	0.9502	0.9514	1115.0	1172.0	0.8384	0.8504	0.8443	roberta-large_L17_no-idf_version=0.3.12(hug_trans=4.53.1)
16.2789	10.0	70	16.6670	0.179	0.0376	0.1311	0.1303	31.0	0.0183	0.0456	0.952	0.9531	1117.0	1172.0	0.839	0.8508	0.8447	roberta-large_L17_no-idf_version=0.3.12(hug_trans=4.53.1)

Framework versions

Transformers 4.53.1
Pytorch 2.7.0+cu126
Datasets 3.6.0
Tokenizers 0.21.1

Library: transformers
Type: longt5
License: apache-2.0
Created: Jul 8, 2025
Updated: Jul 30, 2025